Reproduce “AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jibang Wu, Chenghao Yang, Yi Wu, Simon Mahns, Chaoqi Wang, Hao Zhu, Fei Fang, Haifeng Xu
AI Realtor, an agentic framework leveraging large language models, generates factually grounded persuasive language for automated copywriting in real estate marketing. The system's descriptions were preferred by human subjects over those written by human experts and maintained high factual fidelity.
Key insights
- Economic signaling theory provides a robust framework for designing LLM agents capable of grounded persuasive language generation in commercial applications.
- Fact-grounding, personalization, and highlighting market-surprising features are key components for enhancing the persuasiveness and credibility of AI-generated marketing copy.
- LLMs can generate more compelling and factually accurate marketing content than human experts in specific domains when guided by structured, theory-driven frameworks.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.